postgresql/src/backend/executor/nodeSeqscan.c

329 lines
8.8 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* nodeSeqscan.c
* Support routines for sequential scans of relations.
*
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
2010-09-20 22:08:53 +02:00
* src/backend/executor/nodeSeqscan.c
*
*-------------------------------------------------------------------------
*/
/*
* INTERFACE ROUTINES
* ExecSeqScan sequentially scans a relation.
* ExecSeqNext retrieve next tuple in sequential order.
* ExecInitSeqScan creates and initializes a seqscan node.
* ExecEndSeqScan releases any storage allocated.
* ExecReScanSeqScan rescans the relation
*
* ExecSeqScanEstimate estimates DSM space needed for parallel scan
* ExecSeqScanInitializeDSM initialize DSM for parallel scan
* ExecSeqScanReInitializeDSM reinitialize DSM for fresh parallel scan
* ExecSeqScanInitializeWorker attach to DSM info in parallel worker
*/
#include "postgres.h"
#include "access/relscan.h"
1996-11-08 07:02:30 +01:00
#include "executor/execdebug.h"
#include "executor/nodeSeqscan.h"
#include "utils/rel.h"
static TupleTableSlot *SeqNext(SeqScanState *node);
/* ----------------------------------------------------------------
* Scan Support
* ----------------------------------------------------------------
*/
/* ----------------------------------------------------------------
* SeqNext
*
* This is a workhorse for ExecSeqScan
* ----------------------------------------------------------------
*/
static TupleTableSlot *
SeqNext(SeqScanState *node)
{
HeapTuple tuple;
HeapScanDesc scandesc;
EState *estate;
ScanDirection direction;
TupleTableSlot *slot;
/*
* get information from the estate and scan state
*/
scandesc = node->ss.ss_currentScanDesc;
estate = node->ss.ps.state;
direction = estate->es_direction;
slot = node->ss.ss_ScanTupleSlot;
if (scandesc == NULL)
{
/*
* We reach here if the scan is not parallel, or if we're serially
* executing a scan that was planned to be parallel.
*/
scandesc = heap_beginscan(node->ss.ss_currentRelation,
estate->es_snapshot,
0, NULL);
node->ss.ss_currentScanDesc = scandesc;
}
/*
* get the next tuple from the table
*/
tuple = heap_getnext(scandesc, direction);
/*
2005-10-15 04:49:52 +02:00
* save the tuple and the buffer returned to us by the access methods in
* our scan tuple slot and return the slot. Note: we pass 'false' because
* tuples returned by heap_getnext() are pointers onto disk pages and were
* not created with palloc() and so should not be pfree()'d. Note also
* that ExecStoreHeapTuple will increment the refcount of the buffer; the
2005-10-15 04:49:52 +02:00
* refcount will not be dropped until the tuple table slot is cleared.
*/
if (tuple)
ExecStoreBufferHeapTuple(tuple, /* tuple to store */
slot, /* slot to store in */
scandesc->rs_cbuf); /* buffer associated
* with this tuple */
else
ExecClearTuple(slot);
return slot;
}
/*
* SeqRecheck -- access method routine to recheck a tuple in EvalPlanQual
*/
static bool
SeqRecheck(SeqScanState *node, TupleTableSlot *slot)
{
/*
2010-02-26 03:01:40 +01:00
* Note that unlike IndexScan, SeqScan never use keys in heap_beginscan
* (and this is very bad) - so, here we do not check are keys ok or not.
*/
return true;
}
/* ----------------------------------------------------------------
* ExecSeqScan(node)
*
* Scans the relation sequentially and returns the next qualifying
* tuple.
* We call the ExecScan() routine and pass it the appropriate
* access method functions.
* ----------------------------------------------------------------
*/
static TupleTableSlot *
ExecSeqScan(PlanState *pstate)
{
SeqScanState *node = castNode(SeqScanState, pstate);
return ExecScan(&node->ss,
(ExecScanAccessMtd) SeqNext,
(ExecScanRecheckMtd) SeqRecheck);
}
/* ----------------------------------------------------------------
* ExecInitSeqScan
* ----------------------------------------------------------------
*/
SeqScanState *
ExecInitSeqScan(SeqScan *node, EState *estate, int eflags)
{
SeqScanState *scanstate;
/*
2005-10-15 04:49:52 +02:00
* Once upon a time it was possible to have an outerPlan of a SeqScan, but
* not any more.
*/
Assert(outerPlan(node) == NULL);
Assert(innerPlan(node) == NULL);
/*
* create state structure
*/
scanstate = makeNode(SeqScanState);
scanstate->ss.ps.plan = (Plan *) node;
scanstate->ss.ps.state = estate;
scanstate->ss.ps.ExecProcNode = ExecSeqScan;
/*
* Miscellaneous initialization
*
* create expression context for node
*/
ExecAssignExprContext(estate, &scanstate->ss.ps);
/*
* open the scan relation
*/
scanstate->ss.ss_currentRelation =
ExecOpenScanRelation(estate,
node->scanrelid,
eflags);
/* and create slot with the appropriate rowtype */
ExecInitScanTupleSlot(estate, &scanstate->ss,
Introduce notion of different types of slots (without implementing them). Upcoming work intends to allow pluggable ways to introduce new ways of storing table data. Accessing those table access methods from the executor requires TupleTableSlots to be carry tuples in the native format of such storage methods; otherwise there'll be a significant conversion overhead. Different access methods will require different data to store tuples efficiently (just like virtual, minimal, heap already require fields in TupleTableSlot). To allow that without requiring additional pointer indirections, we want to have different structs (embedding TupleTableSlot) for different types of slots. Thus different types of slots are needed, which requires adapting creators of slots. The slot that most efficiently can represent a type of tuple in an executor node will often depend on the type of slot a child node uses. Therefore we need to track the type of slot is returned by nodes, so parent slots can create slots based on that. Relatedly, JIT compilation of tuple deforming needs to know which type of slot a certain expression refers to, so it can create an appropriate deforming function for the type of tuple in the slot. But not all nodes will only return one type of slot, e.g. an append node will potentially return different types of slots for each of its subplans. Therefore add function that allows to query the type of a node's result slot, and whether it'll always be the same type (whether it's fixed). This can be queried using ExecGetResultSlotOps(). The scan, result, inner, outer type of slots are automatically inferred from ExecInitScanTupleSlot(), ExecInitResultSlot(), left/right subtrees respectively. If that's not correct for a node, that can be overwritten using new fields in PlanState. This commit does not introduce the actually abstracted implementation of different kind of TupleTableSlots, that will be left for a followup commit. The different types of slots introduced will, for now, still use the same backing implementation. While this already partially invalidates the big comment in tuptable.h, it seems to make more sense to update it later, when the different TupleTableSlot implementations actually exist. Author: Ashutosh Bapat and Andres Freund, with changes by Amit Khandekar Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-16 07:00:30 +01:00
RelationGetDescr(scanstate->ss.ss_currentRelation),
Make TupleTableSlots extensible, finish split of existing slot type. This commit completes the work prepared in 1a0586de36, splitting the old TupleTableSlot implementation (which could store buffer, heap, minimal and virtual slots) into four different slot types. As described in the aforementioned commit, this is done with the goal of making tuple table slots extensible, to allow for pluggable table access methods. To achieve runtime extensibility for TupleTableSlots, operations on slots that can differ between types of slots are performed using the TupleTableSlotOps struct provided at slot creation time. That includes information from the size of TupleTableSlot struct to be allocated, initialization, deforming etc. See the struct's definition for more detailed information about callbacks TupleTableSlotOps. I decided to rename TTSOpsBufferTuple to TTSOpsBufferHeapTuple and ExecCopySlotTuple to ExecCopySlotHeapTuple, as that seems more consistent with other naming introduced in recent patches. There's plenty optimization potential in the slot implementation, but according to benchmarking the state after this commit has similar performance characteristics to before this set of changes, which seems sufficient. There's a few changes in execReplication.c that currently need to poke through the slot abstraction, that'll be repaired once the pluggable storage patchset provides the necessary infrastructure. Author: Andres Freund and Ashutosh Bapat, with changes by Amit Khandekar Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-17 01:35:11 +01:00
&TTSOpsBufferHeapTuple);
/*
Don't require return slots for nodes without projection. In a lot of nodes the return slot is not required. That can either be because the node doesn't do any projection (say an Append node), or because the node does perform projections but the projection is optimized away because the projection would yield an identical row. Slots aren't that small, especially for wide rows, so it's worthwhile to avoid creating them. It's not possible to just skip creating the slot - it's currently used to determine the tuple descriptor returned by ExecGetResultType(). So separate the determination of the result type from the slot creation. The work previously done internally ExecInitResultTupleSlotTL() can now also be done separately with ExecInitResultTypeTL() and ExecInitResultSlot(). That way nodes that aren't guaranteed to need a result slot, can use ExecInitResultTypeTL() to determine the result type of the node, and ExecAssignScanProjectionInfo() (via ExecConditionalAssignProjectionInfo()) determines that a result slot is needed, it is created with ExecInitResultSlot(). Besides the advantage of avoiding to create slots that then are unused, this is necessary preparation for later patches around tuple table slot abstraction. In particular separating the return descriptor and slot is a prerequisite to allow JITing of tuple deforming with knowledge of the underlying tuple format, and to avoid unnecessarily creating JITed tuple deforming for virtual slots. This commit removes a redundant argument from ExecInitResultTupleSlotTL(). While this commit touches a lot of the relevant lines anyway, it'd normally still not worthwhile to cause breakage, except that aforementioned later commits will touch *all* ExecInitResultTupleSlotTL() callers anyway (but fits worse thematically). Author: Andres Freund Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-10 02:19:39 +01:00
* Initialize result type and projection.
*/
Don't require return slots for nodes without projection. In a lot of nodes the return slot is not required. That can either be because the node doesn't do any projection (say an Append node), or because the node does perform projections but the projection is optimized away because the projection would yield an identical row. Slots aren't that small, especially for wide rows, so it's worthwhile to avoid creating them. It's not possible to just skip creating the slot - it's currently used to determine the tuple descriptor returned by ExecGetResultType(). So separate the determination of the result type from the slot creation. The work previously done internally ExecInitResultTupleSlotTL() can now also be done separately with ExecInitResultTypeTL() and ExecInitResultSlot(). That way nodes that aren't guaranteed to need a result slot, can use ExecInitResultTypeTL() to determine the result type of the node, and ExecAssignScanProjectionInfo() (via ExecConditionalAssignProjectionInfo()) determines that a result slot is needed, it is created with ExecInitResultSlot(). Besides the advantage of avoiding to create slots that then are unused, this is necessary preparation for later patches around tuple table slot abstraction. In particular separating the return descriptor and slot is a prerequisite to allow JITing of tuple deforming with knowledge of the underlying tuple format, and to avoid unnecessarily creating JITed tuple deforming for virtual slots. This commit removes a redundant argument from ExecInitResultTupleSlotTL(). While this commit touches a lot of the relevant lines anyway, it'd normally still not worthwhile to cause breakage, except that aforementioned later commits will touch *all* ExecInitResultTupleSlotTL() callers anyway (but fits worse thematically). Author: Andres Freund Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-10 02:19:39 +01:00
ExecInitResultTypeTL(&scanstate->ss.ps);
ExecAssignScanProjectionInfo(&scanstate->ss);
/*
* initialize child expressions
*/
scanstate->ss.ps.qual =
ExecInitQual(node->plan.qual, (PlanState *) scanstate);
return scanstate;
}
/* ----------------------------------------------------------------
* ExecEndSeqScan
*
* frees any storage allocated through C routines.
* ----------------------------------------------------------------
*/
void
ExecEndSeqScan(SeqScanState *node)
{
HeapScanDesc scanDesc;
/*
* get information from node
*/
scanDesc = node->ss.ss_currentScanDesc;
/*
* Free the exprcontext
*/
ExecFreeExprContext(&node->ss.ps);
/*
* clean out the tuple table
*/
Don't require return slots for nodes without projection. In a lot of nodes the return slot is not required. That can either be because the node doesn't do any projection (say an Append node), or because the node does perform projections but the projection is optimized away because the projection would yield an identical row. Slots aren't that small, especially for wide rows, so it's worthwhile to avoid creating them. It's not possible to just skip creating the slot - it's currently used to determine the tuple descriptor returned by ExecGetResultType(). So separate the determination of the result type from the slot creation. The work previously done internally ExecInitResultTupleSlotTL() can now also be done separately with ExecInitResultTypeTL() and ExecInitResultSlot(). That way nodes that aren't guaranteed to need a result slot, can use ExecInitResultTypeTL() to determine the result type of the node, and ExecAssignScanProjectionInfo() (via ExecConditionalAssignProjectionInfo()) determines that a result slot is needed, it is created with ExecInitResultSlot(). Besides the advantage of avoiding to create slots that then are unused, this is necessary preparation for later patches around tuple table slot abstraction. In particular separating the return descriptor and slot is a prerequisite to allow JITing of tuple deforming with knowledge of the underlying tuple format, and to avoid unnecessarily creating JITed tuple deforming for virtual slots. This commit removes a redundant argument from ExecInitResultTupleSlotTL(). While this commit touches a lot of the relevant lines anyway, it'd normally still not worthwhile to cause breakage, except that aforementioned later commits will touch *all* ExecInitResultTupleSlotTL() callers anyway (but fits worse thematically). Author: Andres Freund Discussion: https://postgr.es/m/20181105210039.hh4vvi4vwoq5ba2q@alap3.anarazel.de
2018-11-10 02:19:39 +01:00
if (node->ss.ps.ps_ResultTupleSlot)
ExecClearTuple(node->ss.ps.ps_ResultTupleSlot);
ExecClearTuple(node->ss.ss_ScanTupleSlot);
/*
* close heap scan
*/
if (scanDesc != NULL)
heap_endscan(scanDesc);
}
/* ----------------------------------------------------------------
* Join Support
* ----------------------------------------------------------------
*/
/* ----------------------------------------------------------------
* ExecReScanSeqScan
*
* Rescans the relation.
* ----------------------------------------------------------------
*/
void
ExecReScanSeqScan(SeqScanState *node)
{
HeapScanDesc scan;
scan = node->ss.ss_currentScanDesc;
if (scan != NULL)
2016-06-10 00:02:36 +02:00
heap_rescan(scan, /* scan desc */
NULL); /* new scan keys */
ExecScanReScan((ScanState *) node);
}
/* ----------------------------------------------------------------
* Parallel Scan Support
* ----------------------------------------------------------------
*/
/* ----------------------------------------------------------------
* ExecSeqScanEstimate
*
* Compute the amount of space we'll need in the parallel
* query DSM, and inform pcxt->estimator about our needs.
* ----------------------------------------------------------------
*/
void
ExecSeqScanEstimate(SeqScanState *node,
ParallelContext *pcxt)
{
EState *estate = node->ss.ps.state;
node->pscan_len = heap_parallelscan_estimate(estate->es_snapshot);
shm_toc_estimate_chunk(&pcxt->estimator, node->pscan_len);
shm_toc_estimate_keys(&pcxt->estimator, 1);
}
/* ----------------------------------------------------------------
* ExecSeqScanInitializeDSM
*
* Set up a parallel heap scan descriptor.
* ----------------------------------------------------------------
*/
void
ExecSeqScanInitializeDSM(SeqScanState *node,
ParallelContext *pcxt)
{
EState *estate = node->ss.ps.state;
2016-06-10 00:02:36 +02:00
ParallelHeapScanDesc pscan;
pscan = shm_toc_allocate(pcxt->toc, node->pscan_len);
heap_parallelscan_initialize(pscan,
node->ss.ss_currentRelation,
estate->es_snapshot);
shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, pscan);
node->ss.ss_currentScanDesc =
heap_beginscan_parallel(node->ss.ss_currentRelation, pscan);
}
/* ----------------------------------------------------------------
* ExecSeqScanReInitializeDSM
*
* Reset shared state before beginning a fresh scan.
* ----------------------------------------------------------------
*/
void
ExecSeqScanReInitializeDSM(SeqScanState *node,
ParallelContext *pcxt)
{
HeapScanDesc scan = node->ss.ss_currentScanDesc;
heap_parallelscan_reinitialize(scan->rs_parallel);
}
/* ----------------------------------------------------------------
* ExecSeqScanInitializeWorker
*
* Copy relevant information from TOC into planstate.
* ----------------------------------------------------------------
*/
void
ExecSeqScanInitializeWorker(SeqScanState *node,
ParallelWorkerContext *pwcxt)
{
2016-06-10 00:02:36 +02:00
ParallelHeapScanDesc pscan;
pscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
node->ss.ss_currentScanDesc =
heap_beginscan_parallel(node->ss.ss_currentRelation, pscan);
}